GitDiagram
Browse

AI agent architecture examples, page 3

Interactive architecture diagrams of 244 open-source repositories with a GitDiagram architecture diagram where the diagram has an LLM or AI-model component and a component or group named as an agent, most stars first. Each diagram shows the project's main components, how they connect, and links every part to its file on GitHub.

Repositories 101–150 of 244

  1. 1jehuang/jcode★ 21.4k · Rust

    jcode is a high-performance coding-agent application, presented primarily through a terminal UI and backed by a session server.

  2. primeintellect-ai/prime-agent★ 21.3k · Rust

    Prime Agent is a coding and research agent designed for persistent, long-running work.

  3. volcengine/verl★ 21k · Python

    verl is a distributed post-training/RL library for LLMs and VLMs.

  4. alibaba/page-agent★ 20.9k · TypeScript

    This repo is a TypeScript monorepo for “Page Agent”: a client-side agent that controls web pages through DOM/text inspection and LLM-driven actions.

  5. openai/gpt-oss★ 20.4k · Python

    gpt-oss is a collection of open-weight model inference implementations, agent tools, and evaluation programs.

  6. swe-agent/swe-agent★ 20.4k · Python

    SWE-agent is an autonomous software-engineering agent.

  7. eosphoros-ai/db-gpt★ 20.3k · Python

    DB-GPT is an agentic AI data assistant and platform for natural-language data analysis.

  8. pydantic/pydantic-ai★ 20.1k · Python

    Pydantic AI is a typed Python SDK for running model-backed agents across terminal, web, realtime voice, durable execution, and direct APIs.

  9. princeton-nlp/swe-agent★ 20k · Python

    SWE-agent is a Python CLI framework that lets an LLM solve repository tasks through shell-backed tools: issue fixing, benchmarking, custom coding tasks, and legacy CTF workflows.

  10. nvidia-nemo/nemo★ 18.5k · Python

    NeMo Speech is a PyTorch toolkit for building, adapting, and deploying speech and audio models.

  11. arc53/docsgpt★ 18.3k · Python

    DocsGPT is a self-hosted, document-grounded agent platform.

  12. andrewyng/openworker★ 18.2k · Python

    OpenWorker is a local-first desktop AI coworker: a user requests an outcome, the agent works through model/tool iterations across files and connected apps, consequential actions…

  13. langchain-ai/langchainjs★ 18.2k · TypeScript

    LangChain.js is a framework for composing LLM-powered applications from interoperable models, prompts, chains, agents, tools, and retrieval integrations.

  14. google-gemini/gemini-fullstack-langgraph-quickstart★ 18.2k · Jupyter Notebook

    This is a two-tier fullstack repo: a React/Vite frontend in frontend/ and a Python LangGraph backend agent in backend/.

  15. transitive-bullshit/agentic★ 18.1k · TypeScript

    1. Purpose and principal workflow.

  16. google-gemini/cookbook★ 17.8k · Jupyter Notebook

    This is a documentation-and-executable-notebook cookbook for the Gemini API, not a deployable application.

  17. googlecloudplatform/generative-ai★ 17.5k · Jupyter Notebook

    This is a curated Google Cloud generative-AI sample repository, not one deployable product.

  18. nvidia/megatron-lm★ 17.4k · Python

    Megatron-LM combines a reusable GPU-scale deep-learning library (Megatron Core) with reference training applications.

  19. coder/coder★ 17.2k · Go

    Coder is a self-hosted platform for Terraform-defined cloud development workspaces and AI coding agents.

  20. microsoft/data-formulator★ 17.1k · Python

    Data Formulator is a local-first AI-assisted data exploration system: users load/connect data, conduct branching analyses in a Data Thread, generate/refine charts, and compose…

  21. memorilabs/memori★ 17.1k · Python

    Memori is a persistent-memory system for LLM agents, exposed through Python and TypeScript SDKs and agent integrations.

  22. gibsonai/memori★ 17k · Python

    Memori is a persistent-memory SDK and agent integration suite.

  23. qwenlm/qwen-agent★ 16.4k · Python

    - This is the Qwen-Agent framework: a Python SDK for building LLM applications that combine chat, tool use, planning, memory, RAG, and multi-agent orchestration.

  24. hkuds/deepcode★ 16.4k · Python

    DeepCode is a local, multi-interface coding-agent system for durable project work: agent turns can inspect/edit code, execute tools, gather verification evidence, and continue as…

  25. andrewyng/aisuite★ 15.7k · Python

    aisuite is a Python LLM abstraction library with two layers: provider-neutral chat completions and a higher-level agent runtime.

  26. greydgl/pentestgpt★ 15.6k · Python

    PentestGPT offers two workflows: an autonomous staged pipeline for CTF and penetration-test runs, and an interactive legacy mode that maintains a Pentesting Task Tree (PTT).

  27. yc-software/qm★ 15.4k · TypeScript

    QM is a self-hosted multiplayer agent harness: a person starts work in Slack or the web app, the shared core runs a turn through a selectable harness and model, and tools can…

  28. agricidaniel/claude-obsidian★ 15.3k · Python

    claude-obsidian is a local-first knowledge system for Claude Code and compatible Agent Skills hosts.

  29. hkuds/openharness★ 15k · Python

    OpenHarness is a Python agent harness for LLM-driven coding and automation: provider access, iterative tool use, memory, permissions, extensions, and multi-agent work.

  30. microsoft/rd-agent★ 14.8k · Python

    RD-Agent is a framework for autonomous research and development across data science, quantitative finance, Kaggle, LLM fine-tuning, and reinforcement learning.

  31. pipecat-ai/pipecat★ 14.7k · Python

    Pipecat is a Python 3.11+ framework for composing low-latency voice and multimodal AI agents.

  32. livekit/agents★ 14.2k · Python

    This is the Python LiveKit Agents framework: server-side, realtime programmable participants for conversational voice and multimodal sessions.

  33. nanobrowser/nanobrowser★ 13.8k · TypeScript

    Nanobrowser is a Chrome/Edge extension that turns conversational requests into browser automation through a local multi-agent workflow.

  34. browseros-ai/browseros★ 13.8k · TypeScript

    BrowserOS neo is a local, agent-driven secondary browser: users connect MCP-speaking agents, which perform tasks in logged-in browser sessions that can be watched live and…

  35. microsoft/agent-framework★ 13.6k · Python

    Microsoft Agent Framework is a multi-language framework for production AI agents and multi-agent workflows.

  36. nanmicoder/cc-haha★ 13.6k · TypeScript

    Claude Code Haha is a cross-platform local AI coding workbench built around a Claude-Code-derived CLI/runtime, with a React desktop UI, local API server, remote/IM access, and…

  37. aiming-lab/autoresearchclaw★ 13.5k · Python

    - AutoResearchClaw is a Python 3.11+ research orchestration system that turns a topic into a paper through a staged pipeline.

  38. langchain4j/langchain4j★ 13.3k · Java

    LangChain4j is a Java library for building LLM-powered applications, with unified APIs and ready-to-use provider integrations.

  39. qodo-ai/pr-agent★ 13.2k · Python

    PR-Agent is an AI-powered pull-request assistant.

  40. langchain-ai/open_deep_research★ 12.7k · Python

    Open Deep Research is a configurable Python/LangGraph deep-research agent: it turns a user messages request into a sourced research report through iterative search and LLM…

  41. codebuffai/freebuff★ 12.2k · TypeScript

    Freebuff is a Bun/TypeScript monorepo for an AI coding and research platform.

  42. facebookresearch/sam3★ 11.9k · Python

    SAM 3 is a promptable image/video segmentation foundation-model package, with training, evaluation, and an LLM-assisted agent as adjacent capabilities.

  43. krillinai/opencreator★ 11.9k · TypeScript

    OpenCreator is a local AI workspace for creator tools and Codex-powered agent conversations.

  44. beehiveinnovations/pal-mcp-server★ 11.8k · Python

    PAL MCP is an MCP server that lets a CLI or IDE client invoke specialized AI tools, retain conversation context, and use multiple model providers.

  45. akitaonrails/ai-memory★ 11.7k · Rust

    ai-memory is a cross-agent, cross-machine long-term memory system for coding agents.

  46. memtensor/memos★ 11.6k · TypeScript

    MemOS is a memory system for LLM agents, offered as a hosted API, self-hosted service, and agent plugins.

  47. wangrongding/wechat-bot★ 11.4k · JavaScript

    WeChat Bot is a command-line IM agent and local-WeChat analysis tool.

  48. ten-framework/ten-framework★ 11.2k · Python

    TEN is a real-time multimodal conversational AI framework, with a broad catalog of agent extensions and example applications.

  49. spinabot/brigade★ 11.2k · TypeScript

    Brigade is a self-hosted, multi-agent assistant reached through a terminal or messaging channels.

  50. huggingface/skills★ 11.1k · Python

    Hugging Face Skills is a collection of installable, self-contained AI/ML workflow instructions and scripts for agents.

Counted over GitDiagram's stored diagrams of public repositories, from the names their components and groups carry and the files they link to; the rules are the ones in the 2026 open-source architecture report. Stars are GitHub's when the diagram was last made. Rebuilt daily: hubs grow as more repositories' languages are known.